Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Underwater acoustic communication adaptive modulation coding algorithm based on reinforcement learning

An adaptive modulation and reinforcement learning technology, applied in the field of communication systems, can solve the problem that the underwater acoustic channel is difficult to meet the frame error rate requirements, and achieve the effect of solving certain errors

Pending Publication Date: 2022-04-26
JIANGXI UNIV OF SCI & TECH
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the fact that the traditional adaptive modulation and coding algorithm in the underwater acoustic communication system is difficult to meet the frame error rate requirements for complex and changeable underwater acoustic channels, the present invention proposes an adaptive modulation and coding algorithm based on reinforcement learning to solve the above problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Underwater acoustic communication adaptive modulation coding algorithm based on reinforcement learning
  • Underwater acoustic communication adaptive modulation coding algorithm based on reinforcement learning
  • Underwater acoustic communication adaptive modulation coding algorithm based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] 1. In this implementation, the Q-learning algorithm is combined with the adaptive modulation and coding system. First, the three elements of the Q table are defined: state, action, and reward. The signal-to-noise ratio of different sizes in underwater acoustic communication is used as the state state. The modulation method and coding rate selected by the signal-to-noise ratio are used as the action, the throughput obtained by different modulation methods and coding rates is used as the reward, and the Q table is established and initialized.

[0037] 2. In the present invention, the state needs to be discretized first. In the underwater acoustic communication, 0.5dB is used as an interval, and all state spaces are selected between 0-40dB.

[0038] 3. Four modulation modes are selected for the action in the present invention, which are respectively BPSK, QPSK, 16QAM and 32QAM modulation modes. Two error correction coding methods are selected, namely convolutional code and...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the field of underwater acoustic communication, and discloses an underwater acoustic communication adaptive modulation coding algorithm based on reinforcement learning, which autonomously explores the relationship between channel quality and a modulation coding scheme through a reinforcement learning algorithm, and establishes a reliable MCS switching threshold. The method comprises the following steps: firstly, defining a modulation and coding scheme, a signal-to-noise ratio and throughput as three elements state, action and reward of a Q table, initializing the Q table and an initial moment, randomly selecting the modulation and coding scheme to send a signal, receiving a demodulation signal and sending a feedback signal by a receiving end, updating the Q table by a reinforcement learning module according to the feedback information and selecting the modulation and coding scheme to send the signal according to the new Q table, and a receiving end receives the demodulation signal and sends a feedback signal, the above steps are repeated, and an accurate MCS switching threshold is obtained after multiple times of learning by a reinforcement learning module. The problem that a certain error exists in the MCS switching threshold obtained by giving a mathematical model according to simulation or a certain assumption in the traditional adaptive modulation coding technology is solved.

Description

technical field [0001] The invention belongs to the technical field of underwater acoustic communication, and relates to a communication system combining a reinforcement learning algorithm and an adaptive modulation and coding technology. Background technique [0002] Underwater acoustic communication is the most mature communication method in underwater communication, but the underwater acoustic channel has the characteristics of time-varying, space-varying, and frequency-varying. Noise in the ocean, attenuation during signal propagation, multipath propagation, and Doppler frequency These factors directly affect the reliability of underwater acoustic communication. Using channel coding technology to process the information to be sent can effectively resist the interference in the underwater acoustic channel, reduce the bit error rate, and improve the reliability of underwater acoustic communication. As the underwater environment changes all the time, the underwater acousti...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L1/00H04B11/00H04B13/02G06N3/08
CPCH04L1/0017H04L1/0009H04B11/00H04B13/02G06N3/08
Inventor 唐军邓兆才党召凯
Owner JIANGXI UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products